YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.

Comet: agent skill harness for turning ideas into evaluated workflows

One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.

239 evaluated academic Claude/agent skills across 17 research domains (bioinformatics, data science, clinical, social-science methods, Turkish academia & more). Executable eval per skill, deterministic citation verifier, research→write→review→publish pipeline, and a skill-finder front door. Claude Code, Cursor, Codex, Gemini CLI & Copilot.